Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:557e23c2bf963651c89d40069e1bf1ea2ffae25eb725537795da21f54a568434
+oid sha256:16882c1aab2fa604272641a720c9d11c26d57042391146dc37cc479c3c43df0e
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5d088e9abf5cf8ebd528ebdffeebaf9cf0c29176fc4bb1f288310136e106a39
+oid sha256:d27a79e1877d76ad9cc4aac538856fc5014182d9b341e3496ac35939b5a6c962
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:798e5a804c5015a13c256dcddb137fd5521b3a1527698086dacb41e77aa688ca
+oid sha256:ca9d90408da963ffb9fad8ee1462ea336606daceb3aee090813919e2f6738ccd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2063357830047607,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007399186089530152,
+  "best_metric": 2.195878505706787,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00924898261191269,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 7.984,
       "eval_steps_per_second": 3.996,
       "step": 20
+    },
+    {
+      "epoch": 0.00776914539400666,
+      "grad_norm": 0.712395966053009,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.1747,
+      "step": 21
+    },
+    {
+      "epoch": 0.008139104698483167,
+      "grad_norm": 0.6240229606628418,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.9213,
+      "step": 22
+    },
+    {
+      "epoch": 0.008509064002959674,
+      "grad_norm": 0.9065861701965332,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.2728,
+      "step": 23
+    },
+    {
+      "epoch": 0.008879023307436182,
+      "grad_norm": 0.587542712688446,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.0188,
+      "step": 24
+    },
+    {
+      "epoch": 0.00924898261191269,
+      "grad_norm": 0.7155807018280029,
+      "learning_rate": 0.0,
+      "loss": 2.307,
+      "step": 25
+    },
+    {
+      "epoch": 0.00924898261191269,
+      "eval_loss": 2.195878505706787,
+      "eval_runtime": 142.3012,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 4.006,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1640097329971200.0,
+  "total_flos": 2050121662464000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null